print · login   

Luchtbrug is a national digital remote self-monitoring platform created with the goal of tracking the symptoms of asthma patients, to communicate with the health care professionals and find information on, e.g., personalized medication, rescue plan. One of the main goals of this kind of e-health is to reduce the number of regular visits to the outpatient clinic, and increase the monitoring frequency in the home situation. Thus, blended care is introduced with better monitoring and fewer visits. The data is collected from over 20 Dutch hospitals across the Netherlands and comes mostly in the form of various symptom questionnaires. The 68,000 questionnaires have been collected over a period from 2018 to 2023. This dataset is unique in its kind because of its size and scope. The main questionnaire used is the internationally accepted Asthma Control Test (ACT) [1] for children (7 questions, 7-11 years) and adults (5 questions, 12+ years) The questions relate to several features known to patients with asthma. In addition, the dataset includes results from the CARAT [2] questionnaire (related to Asthma and Allergy), consisting of 10 questions.

One important advantage of self-monitoring data lies in the high frequency of measurements, allowing to better separate the measurement error from the underlying signal. However, self-monitoring data comes with its own set of challenges as the lack of a controlled environmental setting increases the number of nuisance factors (time of day, mood, level of rest) [3]. In this project, we will analyze the yearly fluctuations of the questionnaire scores with the goal of finding and understanding patterns in the measurements. We expect that the recorded scores vary depending on the season [4], so the first task will be to extract and confirm any potential seasonality in the data.

For this purpose, we will be employing statistical models suitable for time series analysis like SARIMA [5] or dynamic linear models [6]. Individual patterns may differ and may be influenced by seasonal elements causing severe symptoms (e.g., related to hay fever or viral infections). We also assume a random effect due to the medication, which is meant to reduce the strength of the symptoms suffered by the patients. The medication is similar across centers, but the information on adherence to treatment is missing. Finally, the regional information can also influence the severity of the asthma symptoms through environmental factors such as weather/climate, exposures to air pollution and seasonal allergens such as pollen.

The main research question we want to answer with this project is whether it is possible to recognize seasonal fluctuations in patients with asthma using only the questionnaire data provided by the Luchtbrug platform. A solid understanding of the seasonal patterns are crucial in predicting when peaks and valleys occur in the effects on asthma patients, which will enable clinicians to take appropriate preventative measures and avoid severe situations that require the patient to be hospitalized. A secondary question is whether the seasonality patterns are significantly different across the regions in the Netherlands because of spatial and environmental factors. Taking all of these effects into account can aid in improving the understanding of asthma symptomatology progression across various conditions.

Contact: Gabriel Bucur (RU); Marc Oppelaar (Radboudumc); Peter Merkus (Radboudumc).

[1] https://www.asthmacontroltest.com/en-gb/welcome/

[2] https://www.ipcrg.org/resources/search-resources/carat-10-control-of-allergic-rhinitis-and-asthma-test

[3] https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3951782

[4] https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=9b7f6f8c9bebe26c0aba9bd9930ccf5e43bc9190

[5] https://machinelearningmastery.com/sarima-for-time-series-forecasting-in-python/

[6] https://atsa-es.github.io/atsa-labs/sec-seasonal-dlm-overview.html